Welcome to the community! And thanks for your contribution. I added one comment for your WIP PR. We could have more discussions over there. Thanks!
On Mon, Sep 29, 2025 at 2:45 AM Sai Shashank <[email protected]> wrote: > Hi all, > > While experimenting with different TensorRT versions, I noticed that > compatibility is tied closely to CUDA releases (e.g., TensorRT 8.x → CUDA > 11.x, TensorRT 10.0.1 → CUDA 12.x, TensorRT 10.13 → CUDA 13.x). > > I’m looking for feedback on design direction: > > - > > Should we maintain separate handlers for different TensorRT versions, > or evolve the current handler to target only the latest TensorRT (10.x)? > - > > In the existing code, load_onnx only parses ONNX to an engine but > isn’t used downstream. In my prototype, I added _load_onnx_build_engine, > which directly builds an engine from ONNX and then runs inference. Should > this live in the same handler, or be split into an ONNX-specific handler > separate from TensorRT? > > This is my first open source contribution, so I’d greatly appreciate any > guidance on what would make sense long term for Beam. > >>
